Nora Bakabbey Kulbo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Nora Bakabbey Kulbo has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Prince Clement Addo
Department of Information Technology Education, Akenten Appiah-Menka University of Skills Training and Entrepreneurial Development, Ghana
5 shared publications - Andy Ohemeng Asare
Professor George Brown College 200 King Street East Toronto Ontario Canada
4 shared publications - Samuel Kofi Akpatsa
Faculty of Applied Sciences and Mathematics Education, Akenten Appiah-Menka University of Skills Training and Entrepreneurial Development
3 shared publications - Adasa Nkrumah Kofi Frimpong
University of Electronics Science and Technology of China, Chengdu
1 shared publication - Ato Kwamena Sagoe
Akenten Appiah-Menka University of Skills Training and Entrepreneurial Development
1 shared publication - Boansi Kufuor Oliver
Department of Information Technology, Akenten Appiah-Minka University of Skill Training and Entrepreneurial Development
1 shared publication
Latest Publications
- Open Access
- 20 July 2026
- Published by Akenten Appiah-Menka University of Skills Training and Entrepreneurial Development in Journal of Applied Social Sciences and Entrepreneurship Education
- Vol. 1 (1) , 25-44
Optimizing Credit Risk Assessment in Ghanaian Micro-Lending Institutions: A Comparative Analysis of Random Forest, Extra Tree Classifier, and Ensemble Machine Learning Models
Credit risk assessment is pivotal to the sustainability of micro-lending institutions, particularly in emerging economies such as Ghana, where conventional evaluation methods remain predominantly manual and subjective. Traditional approaches, which rely on face-to-face interviews, personal judgments, and simple background checks, are vulnerable to human biases, inconsistencies, and inefficiencies that contribute to elevated default rates and broader financial instability. This study investigates the application of machine learning (ML) techniques, specifically Random Forest (RF), Extra Tree Classifier (ETC), and a probability-averaged Ensemble Classifier, to enhance credit risk assessment in Ghanaian micro-lending institutions. Using a quantitative experimental research design, the study analysed 32,581 loan records drawn from Tepa Man Microfinance Institution. Data preprocessing included missing-value imputation, one-hot encoding, and class balancing via random oversampling, applied exclusively to the training set. Model performance was evaluated through 10-fold stratified cross-validation using accuracy, precision, recall, F1-score, AUC-ROC, Cohen's Kappa, and Matthews Correlation Coefficient (MCC). Hyperparameters were set to scikit-learn defaults (n_estimators = 100, random_state = 42) to ensure reproducibility. The Random Forest and Extra Tree Classifiers each achieved a mean accuracy of 99.33% and an AUC-ROC of 0.9997, results that are consistent with the high-quality, real-world dataset and are critically interpreted in the context of potential overfitting risks. Feature importance analysis identified the loan-to-income ratio and interest rate as the dominant predictors of default. The Ensemble Method, which averages class probabilities across both base models, achieved 84.25% accuracy and an AUC of 0.9231, demonstrating stronger generalization than the individual classifiers. The study concludes that integrating ML models can substantially improve the accuracy, consistency, and reliability of credit risk evaluations, thereby reducing default rates and supporting financial inclusion in Ghana's microfinance sector.
- 20 July 2026
- Published by Akenten Appiah-Menka University of Skills Training and Entrepreneurial Development in Journal of Applied Social Sciences and Entrepreneurship Education
- Vol. 1 (1) , 25-44
Open AccessOptimizing Credit Risk Assessment in Ghanaian Micro-Lending Institutions: A Comparative Analysis of Random Forest, Extra Tree Classifier, and Ensemble Machine Learning Models
Credit risk assessment is pivotal to the sustainability of micro-lending institutions, particularly in emerging economies such as Ghana, where conventional evaluation methods remain predominantly manual and subjective. Traditional approaches, which rely on face-to-face interviews, personal judgments, and simple background checks, are vulnerable to human biases, inconsistencies, and inefficiencies that contribute to elevated default rates and broader financial instability. This study investigates the application of machine learning (ML) techniques, specifically Random Forest (RF), Extra Tree Classifier (ETC), and a probability-averaged Ensemble Classifier, to enhance credit risk assessment in Ghanaian micro-lending institutions. Using a quantitative experimental research design, the study analysed 32,581 loan records drawn from Tepa Man Microfinance Institution. Data preprocessing included missing-value imputation, one-hot encoding, and class balancing via random oversampling, applied exclusively to the training set. Model performance was evaluated through 10-fold stratified cross-validation using accuracy, precision, recall, F1-score, AUC-ROC, Cohen's Kappa, and Matthews Correlation Coefficient (MCC). Hyperparameters were set to scikit-learn defaults (n_estimators = 100, random_state = 42) to ensure reproducibility. The Random Forest and Extra Tree Classifiers each achieved a mean accuracy of 99.33% and an AUC-ROC of 0.9997, results that are consistent with the high-quality, real-world dataset and are critically interpreted in the context of potential overfitting risks. Feature importance analysis identified the loan-to-income ratio and interest rate as the dominant predictors of default. The Ensemble Method, which averages class probabilities across both base models, achieved 84.25% accuracy and an AUC of 0.9231, demonstrating stronger generalization than the individual classifiers. The study concludes that integrating ML models can substantially improve the accuracy, consistency, and reliability of credit risk evaluations, thereby reducing default rates and supporting financial inclusion in Ghana's microfinance sector.
- 25 April 2022
- Published by Taylor & Francis in Journal of Marketing Theory and Practice
- Vol. 30 (3) , 405-420
Digital analytics approach to understanding short video advertising in digital marketing
This study relied on datasets from global B2C and C2C to investigate the relationship between short video advertising (SV), customer satisfaction, price, quality signals, and sales in digital marketing. Using the web-scraping mining technique, the results from over twenty-three thousand online shops indicate that logistics service quality overrides the relevance of location in digital marketing. SV directly impacts sales and increases the shops’ dynamic scores, including quality of service and customer satisfaction. We identified actual online data to justify why SV adoption is essential in digital marketing and recommend logistic service quality and price fairness to improve sales in e-commerce.
- 25 April 2022
- Published by Taylor & Francis in Journal of Marketing Theory and Practice
- Vol. 30 (3) , 405-420
Digital analytics approach to understanding short video advertising in digital marketing
This study relied on datasets from global B2C and C2C to investigate the relationship between short video advertising (SV), customer satisfaction, price, quality signals, and sales in digital marketing. Using the web-scraping mining technique, the results from over twenty-three thousand online shops indicate that logistics service quality overrides the relevance of location in digital marketing. SV directly impacts sales and increases the shops’ dynamic scores, including quality of service and customer satisfaction. We identified actual online data to justify why SV adoption is essential in digital marketing and recommend logistic service quality and price fairness to improve sales in e-commerce.
- 2 December 2021
- Published by Taylor & Francis in Human Vaccines & Immunotherapeutics
- Vol. 17 (12) , 5063-5068
Guarding against COVID-19 vaccine hesitance in Ghana: analytic view of personal health engagement and vaccine related attitude
Vaccination is the most effective preventive measure against COVID-19 spread. While the WHO and other stakeholders fear vaccine nationalism, vaccine-hesitancy has become a topical issue among experts. Based on the evidence of vaccine hesitancy among Blacks, we explore the interrelatedness of psycho-social factors (personal health engagement, fear of COVID-19, perceived susceptibility, and vaccine-related attitude) likely to thwart vaccine acceptance in Africa. We sampled 1768 Ghanaian adults over 2 weeks from December 14, 2020, the first day a successful COVID-19 vaccine was administered in the US using an online survey. A higher level of personal health engagement was found to promote vaccine-related attitudes while reducing COVID-19 related fears, susceptibility, and vaccine hesitancy. Fear of COVID-19 and perceived vulnerability are significant contributors to the willingness to accept vaccination. This is an indication that health engagement alone will not promote vaccination willingness, but the fear and higher level of perceived susceptibility out of personal evaluation are essential factors in vaccination willingness. We recommend promoting health educational messages on COVID-19 vaccination ahead of any vaccination rollout in Africa, and such messages should contain some element of fear appeal.
- 2 December 2021
- Published by Taylor & Francis in Human Vaccines & Immunotherapeutics
- Vol. 17 (12) , 5063-5068
Guarding against COVID-19 vaccine hesitance in Ghana: analytic view of personal health engagement and vaccine related attitude
Vaccination is the most effective preventive measure against COVID-19 spread. While the WHO and other stakeholders fear vaccine nationalism, vaccine-hesitancy has become a topical issue among experts. Based on the evidence of vaccine hesitancy among Blacks, we explore the interrelatedness of psycho-social factors (personal health engagement, fear of COVID-19, perceived susceptibility, and vaccine-related attitude) likely to thwart vaccine acceptance in Africa. We sampled 1768 Ghanaian adults over 2 weeks from December 14, 2020, the first day a successful COVID-19 vaccine was administered in the US using an online survey. A higher level of personal health engagement was found to promote vaccine-related attitudes while reducing COVID-19 related fears, susceptibility, and vaccine hesitancy. Fear of COVID-19 and perceived vulnerability are significant contributors to the willingness to accept vaccination. This is an indication that health engagement alone will not promote vaccination willingness, but the fear and higher level of perceived susceptibility out of personal evaluation are essential factors in vaccination willingness. We recommend promoting health educational messages on COVID-19 vaccination ahead of any vaccination rollout in Africa, and such messages should contain some element of fear appeal.
- 15 September 2021
- Published by Sciencedomain International in Asian Journal of Research in Computer Science
- p. 52-71
Video Ads in Digital Marketing and Sales: A Big Data Analytics Using Scrapy Web Crawler Mining Technique
The survival of the global economy is rooted in the production of goods, rendering of valuable services, and formulation and implementation of favorable trade policies. These goods and services supported by related policies however, must reach prospective customers unblemished in good time, through planned advertisement strategies. Advertisement over the years has evolved from the traditional one-on-one to technology induced ones such as digital marketing and sales. Technological advancement has diversified advertisement into a multi-faceted and dynamic channel with enormous growth and prospects. In this paper, we made a significant effort to identify actual online data to justify why short video (SV) adoption is essential in e-commerce and digital marketing. A total of 23589 datasets were drawn from three global B2C and C2C websites using the scrappy web crawlers to investigate a resilience model in the relationship between SV advertising adoption, quality signals, customer satisfaction, price fairness, and sales in digital marketing. Whereas shop location is vital in traditional shopping, logistics service quality overrides its influence in online shopping settings.
- 15 September 2021
- Published by Sciencedomain International in Asian Journal of Research in Computer Science
- p. 52-71
Video Ads in Digital Marketing and Sales: A Big Data Analytics Using Scrapy Web Crawler Mining Technique
The survival of the global economy is rooted in the production of goods, rendering of valuable services, and formulation and implementation of favorable trade policies. These goods and services supported by related policies however, must reach prospective customers unblemished in good time, through planned advertisement strategies. Advertisement over the years has evolved from the traditional one-on-one to technology induced ones such as digital marketing and sales. Technological advancement has diversified advertisement into a multi-faceted and dynamic channel with enormous growth and prospects. In this paper, we made a significant effort to identify actual online data to justify why short video (SV) adoption is essential in e-commerce and digital marketing. A total of 23589 datasets were drawn from three global B2C and C2C websites using the scrappy web crawlers to investigate a resilience model in the relationship between SV advertising adoption, quality signals, customer satisfaction, price fairness, and sales in digital marketing. Whereas shop location is vital in traditional shopping, logistics service quality overrides its influence in online shopping settings.
- Top Cited Papers
- 29 March 2021
- Published by Taylor & Francis in The Service Industries Journal
- Vol. 41 (11-12) , 767-786
Customer engagement and purchase intention in live-streaming digital marketing platforms
The lack of human and social cues and customer engagement impedes traditional e-commerce until the birth of social commerce. This study investigates how customer engagement in live-streaming digital marketing affects purchase intentions. The results of 1726 datasets from two e-commerce platforms suggest that customer engagement is significantly associated with followership and purchase intention in live-streaming digital marketing. Whiles price is a significant moderator, its effects become insignificant on their purchase intentions once consumers become followers. The results highlight the positive impacts of social elements, including likes, chats, visits, and exposure time in social commerce towards transactional (purchase) and non-transactional (followership) benefits. Finally, the paper introduces a new perception of measuring customer engagement in live-streaming digital marketing and calls for further research into this new paradigm of social commerce to promote business and service provisions even with the restrictions of COVID-19.
- 29 March 2021
- Published by Taylor & Francis in The Service Industries Journal
- Vol. 41 (11-12) , 767-786
Top Cited PapersCustomer engagement and purchase intention in live-streaming digital marketing platforms
The lack of human and social cues and customer engagement impedes traditional e-commerce until the birth of social commerce. This study investigates how customer engagement in live-streaming digital marketing affects purchase intentions. The results of 1726 datasets from two e-commerce platforms suggest that customer engagement is significantly associated with followership and purchase intention in live-streaming digital marketing. Whiles price is a significant moderator, its effects become insignificant on their purchase intentions once consumers become followers. The results highlight the positive impacts of social elements, including likes, chats, visits, and exposure time in social commerce towards transactional (purchase) and non-transactional (followership) benefits. Finally, the paper introduces a new perception of measuring customer engagement in live-streaming digital marketing and calls for further research into this new paradigm of social commerce to promote business and service provisions even with the restrictions of COVID-19.
- 1 November 2020
- Published by Tech Science Press in Journal of Psychology in Africa
- Vol. 30 (6) , 500-506
Organisational capital and graduate employability: A serial mediation analysis of human and personal-social capital
We explored three resource capitals related to employability (human, personal-social, and organisational) to explain graduate work entry prospects in a developing country setting. Our study sample consisted of 743 final year university students in Ghana and Kenya. Less than half (n = 305) attended an international university in China (females = 37.05%; mean age = 28.89 years, SD = 3.06 years), while 443 attended local universities in Ghana and Kenya (females = 33.12%; mean age = 25.68 years, SD= 2.27 years). Following a serial mediation regression analysis based on 10 000 bootstrap samples at 95% CI, results indicate that organisational capital directly influences graduates’ employability. Human and personal-social capital partially mediates the relationship between organisational capital and graduate employability; increasing employability prospects. The findings suggest that organisational capital, including the prestige of degree- awarding institutions in addition to human capital and personal-social capital, explains graduate employability. We conclude that graduate qualification, institutional affiliation, and the social capital benefit from those affiliations is associated with employability.
- 1 November 2020
- Published by Tech Science Press in Journal of Psychology in Africa
- Vol. 30 (6) , 500-506
Organisational capital and graduate employability: A serial mediation analysis of human and personal-social capital
We explored three resource capitals related to employability (human, personal-social, and organisational) to explain graduate work entry prospects in a developing country setting. Our study sample consisted of 743 final year university students in Ghana and Kenya. Less than half (n = 305) attended an international university in China (females = 37.05%; mean age = 28.89 years, SD = 3.06 years), while 443 attended local universities in Ghana and Kenya (females = 33.12%; mean age = 25.68 years, SD= 2.27 years). Following a serial mediation regression analysis based on 10 000 bootstrap samples at 95% CI, results indicate that organisational capital directly influences graduates’ employability. Human and personal-social capital partially mediates the relationship between organisational capital and graduate employability; increasing employability prospects. The findings suggest that organisational capital, including the prestige of degree- awarding institutions in addition to human capital and personal-social capital, explains graduate employability. We conclude that graduate qualification, institutional affiliation, and the social capital benefit from those affiliations is associated with employability.